Local harness for the Glassbox project: guardrail hooks, agents, and dev-time MCP servers.
Plugin glassbox-harness from marketplace glassbox-harness in HUMBLEF0OL/glassbox. Commands read from the repo's manifest — 1 month ago.
This plugin runs code on your machine — it starts local MCP servers. The exact commands are listed below; read them before installing.
glassbox-conventionsCoding conventions and architectural constraints for the Glassbox repository — ESM-only, zero-dependency, no-network, single normalization boundary, strict layering, one-metric-per-file, graceful degradation. Read when writing or reviewing any code in this repo.
harness-workflowThe Glassbox harness operating loop — how to start a session, work one feature at a time, verify before claiming done, and leave a clean handoff. Based on walkinglabs Learn Harness Engineering. Read at the start of any working session and before claiming completion.
transcript-schemaReference for the Claude Code JSONL transcript schema as consumed by Glassbox — the normalized Event model and the (to-be-confirmed) raw field mapping. Read when working on discover.js, read.js, normalize.js, or classify.js. Update the "Confirmed raw schema" section after the Slice 1 discovery spike
filesystemruns: npx -y @modelcontextprotocol/server-filesystem .
gitruns: uvx mcp-server-git --repository .
Harness-native ECC operator layer - 71 agents, 314 skills, 98 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses
200 skills · 98 commands · 71 agents · 1 MCP server · hooks
Persistent memory for Claude Code: the next session starts where the last one left off.
29 skills · 1 MCP server · hooks
Open-source AI job search that runs locally in your AI coding CLI: scan job portals, evaluate listings into a structured A-H report with a 1-5 score, tailor your CV, track applications
5 skills · hooks
Agentic QE (external: maintained in proffesor-for-testing/agentic-qe, pinned to v3.15.17): a quality-engineering fleet with 11 QE agents, 9 skills, 9 commands, the agentic-qe MCP server pinned to the plugin version, and the aqe-mod guard that refuses destructive operations on AQE learning data
9 skills · 9 commands · 11 agents · 1 MCP server
Skill: add headroom-ai compress() to a Python or TypeScript app to cut LLM input tokens (tool outputs, logs, JSON, chat history). No API key.
1 skill
Build powerful, stateful CLI interfaces for any GUI application using the cli-anything harness methodology.
5 commands
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.